Hugging Face's logo

kaitchup
/
Qwen3.6-27B-autoscheme-3.0bit

Safetensors
qwen3_5
compressed-tensors
Model card Files
xet
 Community
bnjmnmarie commited on
Commit
bdc5bc7
·
verified ·
1 Parent(s): 00e6d86

Upload folder using huggingface_hub

Browse files
Files changed (13) hide show
  1. .gitattributes +1 -0
  2. chat_template.jinja +154 -0
  3. config.json +922 -0
  4. generation_config.json +13 -0
  5. model-00001-of-00004.safetensors +3 -0
  6. model-00002-of-00004.safetensors +3 -0
  7. model-00003-of-00004.safetensors +3 -0
  8. model-00004-of-00004.safetensors +3 -0
  9. model.safetensors.index.json +0 -0
  10. processor_config.json +60 -0
  11. recipe.yaml +265 -0
  12. tokenizer.json +3 -0
  13. tokenizer_config.json +33 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
chat_template.jinja ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set image_count = namespace(value=0) %}
2
+ {%- set video_count = namespace(value=0) %}
3
+ {%- macro render_content(content, do_vision_count, is_system_content=false) %}
4
+ {%- if content is string %}
5
+ {{- content }}
6
+ {%- elif content is iterable and content is not mapping %}
7
+ {%- for item in content %}
8
+ {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
9
+ {%- if is_system_content %}
10
+ {{- raise_exception('System message cannot contain images.') }}
11
+ {%- endif %}
12
+ {%- if do_vision_count %}
13
+ {%- set image_count.value = image_count.value + 1 %}
14
+ {%- endif %}
15
+ {%- if add_vision_id %}
16
+ {{- 'Picture ' ~ image_count.value ~ ': ' }}
17
+ {%- endif %}
18
+ {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
19
+ {%- elif 'video' in item or item.type == 'video' %}
20
+ {%- if is_system_content %}
21
+ {{- raise_exception('System message cannot contain videos.') }}
22
+ {%- endif %}
23
+ {%- if do_vision_count %}
24
+ {%- set video_count.value = video_count.value + 1 %}
25
+ {%- endif %}
26
+ {%- if add_vision_id %}
27
+ {{- 'Video ' ~ video_count.value ~ ': ' }}
28
+ {%- endif %}
29
+ {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
30
+ {%- elif 'text' in item %}
31
+ {{- item.text }}
32
+ {%- else %}
33
+ {{- raise_exception('Unexpected item type in content.') }}
34
+ {%- endif %}
35
+ {%- endfor %}
36
+ {%- elif content is none or content is undefined %}
37
+ {{- '' }}
38
+ {%- else %}
39
+ {{- raise_exception('Unexpected content type.') }}
40
+ {%- endif %}
41
+ {%- endmacro %}
42
+ {%- if not messages %}
43
+ {{- raise_exception('No messages provided.') }}
44
+ {%- endif %}
45
+ {%- if tools and tools is iterable and tools is not mapping %}
46
+ {{- '<|im_start|>system\n' }}
47
+ {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
48
+ {%- for tool in tools %}
49
+ {{- "\n" }}
50
+ {{- tool | tojson }}
51
+ {%- endfor %}
52
+ {{- "\n</tools>" }}
53
+ {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
54
+ {%- if messages[0].role == 'system' %}
55
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
56
+ {%- if content %}
57
+ {{- '\n\n' + content }}
58
+ {%- endif %}
59
+ {%- endif %}
60
+ {{- '<|im_end|>\n' }}
61
+ {%- else %}
62
+ {%- if messages[0].role == 'system' %}
63
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
64
+ {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
65
+ {%- endif %}
66
+ {%- endif %}
67
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
68
+ {%- for message in messages[::-1] %}
69
+ {%- set index = (messages|length - 1) - loop.index0 %}
70
+ {%- if ns.multi_step_tool and message.role == "user" %}
71
+ {%- set content = render_content(message.content, false)|trim %}
72
+ {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
73
+ {%- set ns.multi_step_tool = false %}
74
+ {%- set ns.last_query_index = index %}
75
+ {%- endif %}
76
+ {%- endif %}
77
+ {%- endfor %}
78
+ {%- if ns.multi_step_tool %}
79
+ {{- raise_exception('No user query found in messages.') }}
80
+ {%- endif %}
81
+ {%- for message in messages %}
82
+ {%- set content = render_content(message.content, true)|trim %}
83
+ {%- if message.role == "system" %}
84
+ {%- if not loop.first %}
85
+ {{- raise_exception('System message must be at the beginning.') }}
86
+ {%- endif %}
87
+ {%- elif message.role == "user" %}
88
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
89
+ {%- elif message.role == "assistant" %}
90
+ {%- set reasoning_content = '' %}
91
+ {%- if message.reasoning_content is string %}
92
+ {%- set reasoning_content = message.reasoning_content %}
93
+ {%- else %}
94
+ {%- if '</think>' in content %}
95
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
96
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
97
+ {%- endif %}
98
+ {%- endif %}
99
+ {%- set reasoning_content = reasoning_content|trim %}
100
+ {%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}
101
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
102
+ {%- else %}
103
+ {{- '<|im_start|>' + message.role + '\n' + content }}
104
+ {%- endif %}
105
+ {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
106
+ {%- for tool_call in message.tool_calls %}
107
+ {%- if tool_call.function is defined %}
108
+ {%- set tool_call = tool_call.function %}
109
+ {%- endif %}
110
+ {%- if loop.first %}
111
+ {%- if content|trim %}
112
+ {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
113
+ {%- else %}
114
+ {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
115
+ {%- endif %}
116
+ {%- else %}
117
+ {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
118
+ {%- endif %}
119
+ {%- if tool_call.arguments is defined %}
120
+ {%- for args_name, args_value in tool_call.arguments|items %}
121
+ {{- '<parameter=' + args_name + '>\n' }}
122
+ {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
123
+ {{- args_value }}
124
+ {{- '\n</parameter>\n' }}
125
+ {%- endfor %}
126
+ {%- endif %}
127
+ {{- '</function>\n</tool_call>' }}
128
+ {%- endfor %}
129
+ {%- endif %}
130
+ {{- '<|im_end|>\n' }}
131
+ {%- elif message.role == "tool" %}
132
+ {%- if loop.previtem and loop.previtem.role != "tool" %}
133
+ {{- '<|im_start|>user' }}
134
+ {%- endif %}
135
+ {{- '\n<tool_response>\n' }}
136
+ {{- content }}
137
+ {{- '\n</tool_response>' }}
138
+ {%- if not loop.last and loop.nextitem.role != "tool" %}
139
+ {{- '<|im_end|>\n' }}
140
+ {%- elif loop.last %}
141
+ {{- '<|im_end|>\n' }}
142
+ {%- endif %}
143
+ {%- else %}
144
+ {{- raise_exception('Unexpected message role.') }}
145
+ {%- endif %}
146
+ {%- endfor %}
147
+ {%- if add_generation_prompt %}
148
+ {{- '<|im_start|>assistant\n' }}
149
+ {%- if enable_thinking is defined and enable_thinking is false %}
150
+ {{- '<think>\n\n</think>\n\n' }}
151
+ {%- else %}
152
+ {{- '<think>\n' }}
153
+ {%- endif %}
154
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,922 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5ForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "image_token_id": 248056,
7
+ "language_model_only": false,
8
+ "model_type": "qwen3_5",
9
+ "quantization_config": {
10
+ "config_groups": {
11
+ "group_0": {
12
+ "format": "pack-quantized",
13
+ "input_activations": null,
14
+ "output_activations": null,
15
+ "targets": [
16
+ "model.language_model.layers.0.linear_attn.out_proj"
17
+ ],
18
+ "weights": {
19
+ "actorder": null,
20
+ "block_structure": null,
21
+ "dynamic": false,
22
+ "group_size": 128,
23
+ "num_bits": 4,
24
+ "observer": "memoryless_minmax",
25
+ "observer_kwargs": {},
26
+ "scale_dtype": null,
27
+ "strategy": "group",
28
+ "symmetric": true,
29
+ "type": "int",
30
+ "zp_dtype": null
31
+ }
32
+ },
33
+ "group_1": {
34
+ "format": "pack-quantized",
35
+ "input_activations": null,
36
+ "output_activations": null,
37
+ "targets": [
38
+ "model.language_model.layers.0.linear_attn.in_proj_qkv",
39
+ "model.language_model.layers.0.linear_attn.in_proj_z",
40
+ "model.language_model.layers.0.mlp.down_proj",
41
+ "model.language_model.layers.0.mlp.gate_proj",
42
+ "model.language_model.layers.0.mlp.up_proj",
43
+ "model.language_model.layers.1.linear_attn.in_proj_qkv",
44
+ "model.language_model.layers.1.linear_attn.in_proj_z",
45
+ "model.language_model.layers.1.linear_attn.out_proj",
46
+ "model.language_model.layers.1.mlp.down_proj",
47
+ "model.language_model.layers.1.mlp.gate_proj",
48
+ "model.language_model.layers.1.mlp.up_proj",
49
+ "model.language_model.layers.10.linear_attn.in_proj_qkv",
50
+ "model.language_model.layers.10.linear_attn.in_proj_z",
51
+ "model.language_model.layers.10.linear_attn.out_proj",
52
+ "model.language_model.layers.10.mlp.down_proj",
53
+ "model.language_model.layers.10.mlp.gate_proj",
54
+ "model.language_model.layers.10.mlp.up_proj",
55
+ "model.language_model.layers.11.mlp.down_proj",
56
+ "model.language_model.layers.11.mlp.gate_proj",
57
+ "model.language_model.layers.11.mlp.up_proj",
58
+ "model.language_model.layers.11.self_attn.k_proj",
59
+ "model.language_model.layers.11.self_attn.o_proj",
60
+ "model.language_model.layers.11.self_attn.q_proj",
61
+ "model.language_model.layers.11.self_attn.v_proj",
62
+ "model.language_model.layers.12.linear_attn.in_proj_qkv",
63
+ "model.language_model.layers.12.linear_attn.in_proj_z",
64
+ "model.language_model.layers.12.linear_attn.out_proj",
65
+ "model.language_model.layers.12.mlp.down_proj",
66
+ "model.language_model.layers.12.mlp.gate_proj",
67
+ "model.language_model.layers.12.mlp.up_proj",
68
+ "model.language_model.layers.13.linear_attn.in_proj_qkv",
69
+ "model.language_model.layers.13.linear_attn.in_proj_z",
70
+ "model.language_model.layers.13.linear_attn.out_proj",
71
+ "model.language_model.layers.13.mlp.down_proj",
72
+ "model.language_model.layers.13.mlp.gate_proj",
73
+ "model.language_model.layers.13.mlp.up_proj",
74
+ "model.language_model.layers.14.linear_attn.in_proj_qkv",
75
+ "model.language_model.layers.14.linear_attn.in_proj_z",
76
+ "model.language_model.layers.14.linear_attn.out_proj",
77
+ "model.language_model.layers.14.mlp.down_proj",
78
+ "model.language_model.layers.14.mlp.gate_proj",
79
+ "model.language_model.layers.14.mlp.up_proj",
80
+ "model.language_model.layers.15.mlp.down_proj",
81
+ "model.language_model.layers.15.mlp.gate_proj",
82
+ "model.language_model.layers.15.mlp.up_proj",
83
+ "model.language_model.layers.15.self_attn.k_proj",
84
+ "model.language_model.layers.15.self_attn.o_proj",
85
+ "model.language_model.layers.15.self_attn.q_proj",
86
+ "model.language_model.layers.15.self_attn.v_proj",
87
+ "model.language_model.layers.16.linear_attn.in_proj_qkv",
88
+ "model.language_model.layers.16.linear_attn.in_proj_z",
89
+ "model.language_model.layers.16.linear_attn.out_proj",
90
+ "model.language_model.layers.16.mlp.down_proj",
91
+ "model.language_model.layers.16.mlp.gate_proj",
92
+ "model.language_model.layers.16.mlp.up_proj",
93
+ "model.language_model.layers.17.linear_attn.in_proj_qkv",
94
+ "model.language_model.layers.17.linear_attn.in_proj_z",
95
+ "model.language_model.layers.17.linear_attn.out_proj",
96
+ "model.language_model.layers.17.mlp.down_proj",
97
+ "model.language_model.layers.17.mlp.gate_proj",
98
+ "model.language_model.layers.17.mlp.up_proj",
99
+ "model.language_model.layers.18.linear_attn.in_proj_qkv",
100
+ "model.language_model.layers.18.linear_attn.in_proj_z",
101
+ "model.language_model.layers.18.linear_attn.out_proj",
102
+ "model.language_model.layers.18.mlp.down_proj",
103
+ "model.language_model.layers.18.mlp.gate_proj",
104
+ "model.language_model.layers.18.mlp.up_proj",
105
+ "model.language_model.layers.19.mlp.down_proj",
106
+ "model.language_model.layers.19.mlp.gate_proj",
107
+ "model.language_model.layers.19.mlp.up_proj",
108
+ "model.language_model.layers.19.self_attn.k_proj",
109
+ "model.language_model.layers.19.self_attn.o_proj",
110
+ "model.language_model.layers.19.self_attn.q_proj",
111
+ "model.language_model.layers.19.self_attn.v_proj",
112
+ "model.language_model.layers.2.linear_attn.in_proj_qkv",
113
+ "model.language_model.layers.2.linear_attn.in_proj_z",
114
+ "model.language_model.layers.2.linear_attn.out_proj",
115
+ "model.language_model.layers.2.mlp.down_proj",
116
+ "model.language_model.layers.2.mlp.gate_proj",
117
+ "model.language_model.layers.2.mlp.up_proj",
118
+ "model.language_model.layers.20.linear_attn.in_proj_qkv",
119
+ "model.language_model.layers.20.linear_attn.in_proj_z",
120
+ "model.language_model.layers.20.linear_attn.out_proj",
121
+ "model.language_model.layers.20.mlp.down_proj",
122
+ "model.language_model.layers.20.mlp.gate_proj",
123
+ "model.language_model.layers.20.mlp.up_proj",
124
+ "model.language_model.layers.21.linear_attn.in_proj_qkv",
125
+ "model.language_model.layers.21.linear_attn.in_proj_z",
126
+ "model.language_model.layers.21.linear_attn.out_proj",
127
+ "model.language_model.layers.21.mlp.down_proj",
128
+ "model.language_model.layers.21.mlp.gate_proj",
129
+ "model.language_model.layers.21.mlp.up_proj",
130
+ "model.language_model.layers.22.linear_attn.in_proj_qkv",
131
+ "model.language_model.layers.22.linear_attn.in_proj_z",
132
+ "model.language_model.layers.22.linear_attn.out_proj",
133
+ "model.language_model.layers.22.mlp.down_proj",
134
+ "model.language_model.layers.22.mlp.gate_proj",
135
+ "model.language_model.layers.22.mlp.up_proj",
136
+ "model.language_model.layers.23.mlp.down_proj",
137
+ "model.language_model.layers.23.mlp.gate_proj",
138
+ "model.language_model.layers.23.mlp.up_proj",
139
+ "model.language_model.layers.23.self_attn.k_proj",
140
+ "model.language_model.layers.23.self_attn.o_proj",
141
+ "model.language_model.layers.23.self_attn.q_proj",
142
+ "model.language_model.layers.23.self_attn.v_proj",
143
+ "model.language_model.layers.24.linear_attn.in_proj_qkv",
144
+ "model.language_model.layers.24.linear_attn.in_proj_z",
145
+ "model.language_model.layers.24.linear_attn.out_proj",
146
+ "model.language_model.layers.24.mlp.down_proj",
147
+ "model.language_model.layers.24.mlp.gate_proj",
148
+ "model.language_model.layers.24.mlp.up_proj",
149
+ "model.language_model.layers.25.linear_attn.in_proj_qkv",
150
+ "model.language_model.layers.25.linear_attn.in_proj_z",
151
+ "model.language_model.layers.25.linear_attn.out_proj",
152
+ "model.language_model.layers.25.mlp.down_proj",
153
+ "model.language_model.layers.25.mlp.gate_proj",
154
+ "model.language_model.layers.25.mlp.up_proj",
155
+ "model.language_model.layers.26.linear_attn.in_proj_qkv",
156
+ "model.language_model.layers.26.linear_attn.in_proj_z",
157
+ "model.language_model.layers.26.linear_attn.out_proj",
158
+ "model.language_model.layers.26.mlp.down_proj",
159
+ "model.language_model.layers.26.mlp.gate_proj",
160
+ "model.language_model.layers.26.mlp.up_proj",
161
+ "model.language_model.layers.27.mlp.down_proj",
162
+ "model.language_model.layers.27.mlp.gate_proj",
163
+ "model.language_model.layers.27.mlp.up_proj",
164
+ "model.language_model.layers.27.self_attn.k_proj",
165
+ "model.language_model.layers.27.self_attn.o_proj",
166
+ "model.language_model.layers.27.self_attn.q_proj",
167
+ "model.language_model.layers.27.self_attn.v_proj",
168
+ "model.language_model.layers.28.linear_attn.in_proj_qkv",
169
+ "model.language_model.layers.28.linear_attn.in_proj_z",
170
+ "model.language_model.layers.28.linear_attn.out_proj",
171
+ "model.language_model.layers.28.mlp.down_proj",
172
+ "model.language_model.layers.28.mlp.gate_proj",
173
+ "model.language_model.layers.28.mlp.up_proj",
174
+ "model.language_model.layers.29.linear_attn.in_proj_qkv",
175
+ "model.language_model.layers.29.linear_attn.in_proj_z",
176
+ "model.language_model.layers.29.linear_attn.out_proj",
177
+ "model.language_model.layers.29.mlp.down_proj",
178
+ "model.language_model.layers.29.mlp.gate_proj",
179
+ "model.language_model.layers.29.mlp.up_proj",
180
+ "model.language_model.layers.3.mlp.down_proj",
181
+ "model.language_model.layers.3.mlp.gate_proj",
182
+ "model.language_model.layers.3.mlp.up_proj",
183
+ "model.language_model.layers.3.self_attn.k_proj",
184
+ "model.language_model.layers.3.self_attn.o_proj",
185
+ "model.language_model.layers.3.self_attn.q_proj",
186
+ "model.language_model.layers.3.self_attn.v_proj",
187
+ "model.language_model.layers.30.linear_attn.in_proj_qkv",
188
+ "model.language_model.layers.30.linear_attn.in_proj_z",
189
+ "model.language_model.layers.30.linear_attn.out_proj",
190
+ "model.language_model.layers.30.mlp.down_proj",
191
+ "model.language_model.layers.30.mlp.gate_proj",
192
+ "model.language_model.layers.30.mlp.up_proj",
193
+ "model.language_model.layers.31.mlp.down_proj",
194
+ "model.language_model.layers.31.mlp.gate_proj",
195
+ "model.language_model.layers.31.mlp.up_proj",
196
+ "model.language_model.layers.31.self_attn.k_proj",
197
+ "model.language_model.layers.31.self_attn.o_proj",
198
+ "model.language_model.layers.31.self_attn.q_proj",
199
+ "model.language_model.layers.31.self_attn.v_proj",
200
+ "model.language_model.layers.32.linear_attn.in_proj_qkv",
201
+ "model.language_model.layers.32.linear_attn.in_proj_z",
202
+ "model.language_model.layers.32.linear_attn.out_proj",
203
+ "model.language_model.layers.32.mlp.down_proj",
204
+ "model.language_model.layers.32.mlp.gate_proj",
205
+ "model.language_model.layers.32.mlp.up_proj",
206
+ "model.language_model.layers.33.linear_attn.in_proj_qkv",
207
+ "model.language_model.layers.33.linear_attn.in_proj_z",
208
+ "model.language_model.layers.33.linear_attn.out_proj",
209
+ "model.language_model.layers.33.mlp.down_proj",
210
+ "model.language_model.layers.33.mlp.gate_proj",
211
+ "model.language_model.layers.33.mlp.up_proj",
212
+ "model.language_model.layers.34.linear_attn.in_proj_qkv",
213
+ "model.language_model.layers.34.linear_attn.in_proj_z",
214
+ "model.language_model.layers.34.linear_attn.out_proj",
215
+ "model.language_model.layers.34.mlp.down_proj",
216
+ "model.language_model.layers.34.mlp.gate_proj",
217
+ "model.language_model.layers.34.mlp.up_proj",
218
+ "model.language_model.layers.35.mlp.down_proj",
219
+ "model.language_model.layers.35.mlp.gate_proj",
220
+ "model.language_model.layers.35.mlp.up_proj",
221
+ "model.language_model.layers.35.self_attn.k_proj",
222
+ "model.language_model.layers.35.self_attn.o_proj",
223
+ "model.language_model.layers.35.self_attn.q_proj",
224
+ "model.language_model.layers.35.self_attn.v_proj",
225
+ "model.language_model.layers.36.linear_attn.in_proj_qkv",
226
+ "model.language_model.layers.36.linear_attn.in_proj_z",
227
+ "model.language_model.layers.36.linear_attn.out_proj",
228
+ "model.language_model.layers.36.mlp.down_proj",
229
+ "model.language_model.layers.36.mlp.gate_proj",
230
+ "model.language_model.layers.36.mlp.up_proj",
231
+ "model.language_model.layers.37.linear_attn.in_proj_qkv",
232
+ "model.language_model.layers.37.linear_attn.in_proj_z",
233
+ "model.language_model.layers.37.linear_attn.out_proj",
234
+ "model.language_model.layers.37.mlp.down_proj",
235
+ "model.language_model.layers.37.mlp.gate_proj",
236
+ "model.language_model.layers.37.mlp.up_proj",
237
+ "model.language_model.layers.38.linear_attn.in_proj_qkv",
238
+ "model.language_model.layers.38.linear_attn.in_proj_z",
239
+ "model.language_model.layers.38.linear_attn.out_proj",
240
+ "model.language_model.layers.38.mlp.down_proj",
241
+ "model.language_model.layers.38.mlp.gate_proj",
242
+ "model.language_model.layers.38.mlp.up_proj",
243
+ "model.language_model.layers.39.mlp.down_proj",
244
+ "model.language_model.layers.39.mlp.gate_proj",
245
+ "model.language_model.layers.39.mlp.up_proj",
246
+ "model.language_model.layers.39.self_attn.k_proj",
247
+ "model.language_model.layers.39.self_attn.o_proj",
248
+ "model.language_model.layers.39.self_attn.q_proj",
249
+ "model.language_model.layers.39.self_attn.v_proj",
250
+ "model.language_model.layers.4.linear_attn.in_proj_qkv",
251
+ "model.language_model.layers.4.linear_attn.in_proj_z",
252
+ "model.language_model.layers.4.linear_attn.out_proj",
253
+ "model.language_model.layers.4.mlp.down_proj",
254
+ "model.language_model.layers.4.mlp.gate_proj",
255
+ "model.language_model.layers.4.mlp.up_proj",
256
+ "model.language_model.layers.40.linear_attn.in_proj_qkv",
257
+ "model.language_model.layers.40.linear_attn.in_proj_z",
258
+ "model.language_model.layers.40.linear_attn.out_proj",
259
+ "model.language_model.layers.40.mlp.down_proj",
260
+ "model.language_model.layers.40.mlp.gate_proj",
261
+ "model.language_model.layers.40.mlp.up_proj",
262
+ "model.language_model.layers.41.linear_attn.in_proj_qkv",
263
+ "model.language_model.layers.41.linear_attn.in_proj_z",
264
+ "model.language_model.layers.41.linear_attn.out_proj",
265
+ "model.language_model.layers.41.mlp.down_proj",
266
+ "model.language_model.layers.41.mlp.gate_proj",
267
+ "model.language_model.layers.41.mlp.up_proj",
268
+ "model.language_model.layers.42.linear_attn.in_proj_qkv",
269
+ "model.language_model.layers.42.linear_attn.in_proj_z",
270
+ "model.language_model.layers.42.linear_attn.out_proj",
271
+ "model.language_model.layers.42.mlp.down_proj",
272
+ "model.language_model.layers.42.mlp.gate_proj",
273
+ "model.language_model.layers.42.mlp.up_proj",
274
+ "model.language_model.layers.43.mlp.down_proj",
275
+ "model.language_model.layers.43.mlp.gate_proj",
276
+ "model.language_model.layers.43.mlp.up_proj",
277
+ "model.language_model.layers.43.self_attn.k_proj",
278
+ "model.language_model.layers.43.self_attn.o_proj",
279
+ "model.language_model.layers.43.self_attn.q_proj",
280
+ "model.language_model.layers.43.self_attn.v_proj",
281
+ "model.language_model.layers.44.linear_attn.in_proj_qkv",
282
+ "model.language_model.layers.44.linear_attn.in_proj_z",
283
+ "model.language_model.layers.44.linear_attn.out_proj",
284
+ "model.language_model.layers.44.mlp.down_proj",
285
+ "model.language_model.layers.44.mlp.gate_proj",
286
+ "model.language_model.layers.44.mlp.up_proj",
287
+ "model.language_model.layers.45.linear_attn.in_proj_qkv",
288
+ "model.language_model.layers.45.linear_attn.in_proj_z",
289
+ "model.language_model.layers.45.linear_attn.out_proj",
290
+ "model.language_model.layers.45.mlp.down_proj",
291
+ "model.language_model.layers.45.mlp.gate_proj",
292
+ "model.language_model.layers.45.mlp.up_proj",
293
+ "model.language_model.layers.46.linear_attn.in_proj_qkv",
294
+ "model.language_model.layers.46.linear_attn.in_proj_z",
295
+ "model.language_model.layers.46.linear_attn.out_proj",
296
+ "model.language_model.layers.46.mlp.down_proj",
297
+ "model.language_model.layers.46.mlp.gate_proj",
298
+ "model.language_model.layers.46.mlp.up_proj",
299
+ "model.language_model.layers.47.mlp.down_proj",
300
+ "model.language_model.layers.47.mlp.gate_proj",
301
+ "model.language_model.layers.47.mlp.up_proj",
302
+ "model.language_model.layers.47.self_attn.k_proj",
303
+ "model.language_model.layers.47.self_attn.o_proj",
304
+ "model.language_model.layers.47.self_attn.q_proj",
305
+ "model.language_model.layers.47.self_attn.v_proj",
306
+ "model.language_model.layers.48.linear_attn.in_proj_qkv",
307
+ "model.language_model.layers.48.linear_attn.in_proj_z",
308
+ "model.language_model.layers.48.linear_attn.out_proj",
309
+ "model.language_model.layers.48.mlp.down_proj",
310
+ "model.language_model.layers.48.mlp.gate_proj",
311
+ "model.language_model.layers.48.mlp.up_proj",
312
+ "model.language_model.layers.49.linear_attn.in_proj_qkv",
313
+ "model.language_model.layers.49.linear_attn.in_proj_z",
314
+ "model.language_model.layers.49.linear_attn.out_proj",
315
+ "model.language_model.layers.49.mlp.down_proj",
316
+ "model.language_model.layers.49.mlp.gate_proj",
317
+ "model.language_model.layers.49.mlp.up_proj",
318
+ "model.language_model.layers.5.linear_attn.in_proj_qkv",
319
+ "model.language_model.layers.5.linear_attn.in_proj_z",
320
+ "model.language_model.layers.5.linear_attn.out_proj",
321
+ "model.language_model.layers.5.mlp.down_proj",
322
+ "model.language_model.layers.5.mlp.gate_proj",
323
+ "model.language_model.layers.5.mlp.up_proj",
324
+ "model.language_model.layers.50.linear_attn.in_proj_qkv",
325
+ "model.language_model.layers.50.linear_attn.in_proj_z",
326
+ "model.language_model.layers.50.linear_attn.out_proj",
327
+ "model.language_model.layers.50.mlp.down_proj",
328
+ "model.language_model.layers.50.mlp.gate_proj",
329
+ "model.language_model.layers.50.mlp.up_proj",
330
+ "model.language_model.layers.51.mlp.down_proj",
331
+ "model.language_model.layers.51.mlp.gate_proj",
332
+ "model.language_model.layers.51.mlp.up_proj",
333
+ "model.language_model.layers.51.self_attn.k_proj",
334
+ "model.language_model.layers.51.self_attn.o_proj",
335
+ "model.language_model.layers.51.self_attn.q_proj",
336
+ "model.language_model.layers.51.self_attn.v_proj",
337
+ "model.language_model.layers.52.linear_attn.in_proj_qkv",
338
+ "model.language_model.layers.52.linear_attn.in_proj_z",
339
+ "model.language_model.layers.52.linear_attn.out_proj",
340
+ "model.language_model.layers.52.mlp.down_proj",
341
+ "model.language_model.layers.52.mlp.gate_proj",
342
+ "model.language_model.layers.52.mlp.up_proj",
343
+ "model.language_model.layers.53.linear_attn.in_proj_qkv",
344
+ "model.language_model.layers.53.linear_attn.in_proj_z",
345
+ "model.language_model.layers.53.linear_attn.out_proj",
346
+ "model.language_model.layers.53.mlp.down_proj",
347
+ "model.language_model.layers.53.mlp.gate_proj",
348
+ "model.language_model.layers.53.mlp.up_proj",
349
+ "model.language_model.layers.54.linear_attn.in_proj_qkv",
350
+ "model.language_model.layers.54.linear_attn.in_proj_z",
351
+ "model.language_model.layers.54.linear_attn.out_proj",
352
+ "model.language_model.layers.54.mlp.down_proj",
353
+ "model.language_model.layers.54.mlp.gate_proj",
354
+ "model.language_model.layers.54.mlp.up_proj",
355
+ "model.language_model.layers.55.mlp.down_proj",
356
+ "model.language_model.layers.55.mlp.gate_proj",
357
+ "model.language_model.layers.55.mlp.up_proj",
358
+ "model.language_model.layers.55.self_attn.k_proj",
359
+ "model.language_model.layers.55.self_attn.o_proj",
360
+ "model.language_model.layers.55.self_attn.q_proj",
361
+ "model.language_model.layers.55.self_attn.v_proj",
362
+ "model.language_model.layers.56.linear_attn.in_proj_qkv",
363
+ "model.language_model.layers.56.linear_attn.in_proj_z",
364
+ "model.language_model.layers.56.linear_attn.out_proj",
365
+ "model.language_model.layers.56.mlp.down_proj",
366
+ "model.language_model.layers.56.mlp.gate_proj",
367
+ "model.language_model.layers.56.mlp.up_proj",
368
+ "model.language_model.layers.57.linear_attn.in_proj_qkv",
369
+ "model.language_model.layers.57.linear_attn.in_proj_z",
370
+ "model.language_model.layers.57.linear_attn.out_proj",
371
+ "model.language_model.layers.57.mlp.down_proj",
372
+ "model.language_model.layers.57.mlp.gate_proj",
373
+ "model.language_model.layers.57.mlp.up_proj",
374
+ "model.language_model.layers.58.linear_attn.in_proj_qkv",
375
+ "model.language_model.layers.58.linear_attn.in_proj_z",
376
+ "model.language_model.layers.58.linear_attn.out_proj",
377
+ "model.language_model.layers.58.mlp.down_proj",
378
+ "model.language_model.layers.58.mlp.gate_proj",
379
+ "model.language_model.layers.58.mlp.up_proj",
380
+ "model.language_model.layers.59.mlp.down_proj",
381
+ "model.language_model.layers.59.mlp.gate_proj",
382
+ "model.language_model.layers.59.mlp.up_proj",
383
+ "model.language_model.layers.59.self_attn.k_proj",
384
+ "model.language_model.layers.59.self_attn.o_proj",
385
+ "model.language_model.layers.59.self_attn.q_proj",
386
+ "model.language_model.layers.59.self_attn.v_proj",
387
+ "model.language_model.layers.6.linear_attn.in_proj_qkv",
388
+ "model.language_model.layers.6.linear_attn.in_proj_z",
389
+ "model.language_model.layers.6.linear_attn.out_proj",
390
+ "model.language_model.layers.6.mlp.down_proj",
391
+ "model.language_model.layers.6.mlp.gate_proj",
392
+ "model.language_model.layers.6.mlp.up_proj",
393
+ "model.language_model.layers.60.linear_attn.out_proj",
394
+ "model.language_model.layers.60.mlp.down_proj",
395
+ "model.language_model.layers.60.mlp.gate_proj",
396
+ "model.language_model.layers.60.mlp.up_proj",
397
+ "model.language_model.layers.61.linear_attn.out_proj",
398
+ "model.language_model.layers.61.mlp.down_proj",
399
+ "model.language_model.layers.61.mlp.gate_proj",
400
+ "model.language_model.layers.61.mlp.up_proj",
401
+ "model.language_model.layers.62.linear_attn.in_proj_qkv",
402
+ "model.language_model.layers.62.linear_attn.in_proj_z",
403
+ "model.language_model.layers.62.linear_attn.out_proj",
404
+ "model.language_model.layers.62.mlp.down_proj",
405
+ "model.language_model.layers.63.mlp.down_proj",
406
+ "model.language_model.layers.63.mlp.gate_proj",
407
+ "model.language_model.layers.63.mlp.up_proj",
408
+ "model.language_model.layers.63.self_attn.k_proj",
409
+ "model.language_model.layers.63.self_attn.o_proj",
410
+ "model.language_model.layers.63.self_attn.q_proj",
411
+ "model.language_model.layers.63.self_attn.v_proj",
412
+ "model.language_model.layers.7.mlp.down_proj",
413
+ "model.language_model.layers.7.mlp.gate_proj",
414
+ "model.language_model.layers.7.mlp.up_proj",
415
+ "model.language_model.layers.7.self_attn.k_proj",
416
+ "model.language_model.layers.7.self_attn.o_proj",
417
+ "model.language_model.layers.7.self_attn.q_proj",
418
+ "model.language_model.layers.7.self_attn.v_proj",
419
+ "model.language_model.layers.8.linear_attn.in_proj_qkv",
420
+ "model.language_model.layers.8.linear_attn.in_proj_z",
421
+ "model.language_model.layers.8.linear_attn.out_proj",
422
+ "model.language_model.layers.8.mlp.down_proj",
423
+ "model.language_model.layers.8.mlp.gate_proj",
424
+ "model.language_model.layers.8.mlp.up_proj",
425
+ "model.language_model.layers.9.linear_attn.in_proj_qkv",
426
+ "model.language_model.layers.9.linear_attn.in_proj_z",
427
+ "model.language_model.layers.9.linear_attn.out_proj",
428
+ "model.language_model.layers.9.mlp.down_proj",
429
+ "model.language_model.layers.9.mlp.gate_proj",
430
+ "model.language_model.layers.9.mlp.up_proj"
431
+ ],
432
+ "weights": {
433
+ "actorder": null,
434
+ "block_structure": null,
435
+ "dynamic": false,
436
+ "group_size": 128,
437
+ "num_bits": 3,
438
+ "observer": "memoryless_minmax",
439
+ "observer_kwargs": {},
440
+ "scale_dtype": null,
441
+ "strategy": "group",
442
+ "symmetric": true,
443
+ "type": "int",
444
+ "zp_dtype": null
445
+ }
446
+ },
447
+ "group_2": {
448
+ "format": "pack-quantized",
449
+ "input_activations": null,
450
+ "output_activations": null,
451
+ "targets": [
452
+ "model.language_model.layers.60.linear_attn.in_proj_qkv",
453
+ "model.language_model.layers.60.linear_attn.in_proj_z",
454
+ "model.language_model.layers.61.linear_attn.in_proj_qkv",
455
+ "model.language_model.layers.61.linear_attn.in_proj_z",
456
+ "model.language_model.layers.62.mlp.gate_proj",
457
+ "model.language_model.layers.62.mlp.up_proj"
458
+ ],
459
+ "weights": {
460
+ "actorder": null,
461
+ "block_structure": null,
462
+ "dynamic": false,
463
+ "group_size": 128,
464
+ "num_bits": 2,
465
+ "observer": "memoryless_minmax",
466
+ "observer_kwargs": {},
467
+ "scale_dtype": null,
468
+ "strategy": "group",
469
+ "symmetric": true,
470
+ "type": "int",
471
+ "zp_dtype": null
472
+ }
473
+ }
474
+ },
475
+ "format": "pack-quantized",
476
+ "global_compression_ratio": null,
477
+ "ignore": [
478
+ "model.visual.blocks.0.attn.qkv",
479
+ "model.visual.blocks.0.attn.proj",
480
+ "model.visual.blocks.0.mlp.linear_fc1",
481
+ "model.visual.blocks.0.mlp.linear_fc2",
482
+ "model.visual.blocks.1.attn.qkv",
483
+ "model.visual.blocks.1.attn.proj",
484
+ "model.visual.blocks.1.mlp.linear_fc1",
485
+ "model.visual.blocks.1.mlp.linear_fc2",
486
+ "model.visual.blocks.2.attn.qkv",
487
+ "model.visual.blocks.2.attn.proj",
488
+ "model.visual.blocks.2.mlp.linear_fc1",
489
+ "model.visual.blocks.2.mlp.linear_fc2",
490
+ "model.visual.blocks.3.attn.qkv",
491
+ "model.visual.blocks.3.attn.proj",
492
+ "model.visual.blocks.3.mlp.linear_fc1",
493
+ "model.visual.blocks.3.mlp.linear_fc2",
494
+ "model.visual.blocks.4.attn.qkv",
495
+ "model.visual.blocks.4.attn.proj",
496
+ "model.visual.blocks.4.mlp.linear_fc1",
497
+ "model.visual.blocks.4.mlp.linear_fc2",
498
+ "model.visual.blocks.5.attn.qkv",
499
+ "model.visual.blocks.5.attn.proj",
500
+ "model.visual.blocks.5.mlp.linear_fc1",
501
+ "model.visual.blocks.5.mlp.linear_fc2",
502
+ "model.visual.blocks.6.attn.qkv",
503
+ "model.visual.blocks.6.attn.proj",
504
+ "model.visual.blocks.6.mlp.linear_fc1",
505
+ "model.visual.blocks.6.mlp.linear_fc2",
506
+ "model.visual.blocks.7.attn.qkv",
507
+ "model.visual.blocks.7.attn.proj",
508
+ "model.visual.blocks.7.mlp.linear_fc1",
509
+ "model.visual.blocks.7.mlp.linear_fc2",
510
+ "model.visual.blocks.8.attn.qkv",
511
+ "model.visual.blocks.8.attn.proj",
512
+ "model.visual.blocks.8.mlp.linear_fc1",
513
+ "model.visual.blocks.8.mlp.linear_fc2",
514
+ "model.visual.blocks.9.attn.qkv",
515
+ "model.visual.blocks.9.attn.proj",
516
+ "model.visual.blocks.9.mlp.linear_fc1",
517
+ "model.visual.blocks.9.mlp.linear_fc2",
518
+ "model.visual.blocks.10.attn.qkv",
519
+ "model.visual.blocks.10.attn.proj",
520
+ "model.visual.blocks.10.mlp.linear_fc1",
521
+ "model.visual.blocks.10.mlp.linear_fc2",
522
+ "model.visual.blocks.11.attn.qkv",
523
+ "model.visual.blocks.11.attn.proj",
524
+ "model.visual.blocks.11.mlp.linear_fc1",
525
+ "model.visual.blocks.11.mlp.linear_fc2",
526
+ "model.visual.blocks.12.attn.qkv",
527
+ "model.visual.blocks.12.attn.proj",
528
+ "model.visual.blocks.12.mlp.linear_fc1",
529
+ "model.visual.blocks.12.mlp.linear_fc2",
530
+ "model.visual.blocks.13.attn.qkv",
531
+ "model.visual.blocks.13.attn.proj",
532
+ "model.visual.blocks.13.mlp.linear_fc1",
533
+ "model.visual.blocks.13.mlp.linear_fc2",
534
+ "model.visual.blocks.14.attn.qkv",
535
+ "model.visual.blocks.14.attn.proj",
536
+ "model.visual.blocks.14.mlp.linear_fc1",
537
+ "model.visual.blocks.14.mlp.linear_fc2",
538
+ "model.visual.blocks.15.attn.qkv",
539
+ "model.visual.blocks.15.attn.proj",
540
+ "model.visual.blocks.15.mlp.linear_fc1",
541
+ "model.visual.blocks.15.mlp.linear_fc2",
542
+ "model.visual.blocks.16.attn.qkv",
543
+ "model.visual.blocks.16.attn.proj",
544
+ "model.visual.blocks.16.mlp.linear_fc1",
545
+ "model.visual.blocks.16.mlp.linear_fc2",
546
+ "model.visual.blocks.17.attn.qkv",
547
+ "model.visual.blocks.17.attn.proj",
548
+ "model.visual.blocks.17.mlp.linear_fc1",
549
+ "model.visual.blocks.17.mlp.linear_fc2",
550
+ "model.visual.blocks.18.attn.qkv",
551
+ "model.visual.blocks.18.attn.proj",
552
+ "model.visual.blocks.18.mlp.linear_fc1",
553
+ "model.visual.blocks.18.mlp.linear_fc2",
554
+ "model.visual.blocks.19.attn.qkv",
555
+ "model.visual.blocks.19.attn.proj",
556
+ "model.visual.blocks.19.mlp.linear_fc1",
557
+ "model.visual.blocks.19.mlp.linear_fc2",
558
+ "model.visual.blocks.20.attn.qkv",
559
+ "model.visual.blocks.20.attn.proj",
560
+ "model.visual.blocks.20.mlp.linear_fc1",
561
+ "model.visual.blocks.20.mlp.linear_fc2",
562
+ "model.visual.blocks.21.attn.qkv",
563
+ "model.visual.blocks.21.attn.proj",
564
+ "model.visual.blocks.21.mlp.linear_fc1",
565
+ "model.visual.blocks.21.mlp.linear_fc2",
566
+ "model.visual.blocks.22.attn.qkv",
567
+ "model.visual.blocks.22.attn.proj",
568
+ "model.visual.blocks.22.mlp.linear_fc1",
569
+ "model.visual.blocks.22.mlp.linear_fc2",
570
+ "model.visual.blocks.23.attn.qkv",
571
+ "model.visual.blocks.23.attn.proj",
572
+ "model.visual.blocks.23.mlp.linear_fc1",
573
+ "model.visual.blocks.23.mlp.linear_fc2",
574
+ "model.visual.blocks.24.attn.qkv",
575
+ "model.visual.blocks.24.attn.proj",
576
+ "model.visual.blocks.24.mlp.linear_fc1",
577
+ "model.visual.blocks.24.mlp.linear_fc2",
578
+ "model.visual.blocks.25.attn.qkv",
579
+ "model.visual.blocks.25.attn.proj",
580
+ "model.visual.blocks.25.mlp.linear_fc1",
581
+ "model.visual.blocks.25.mlp.linear_fc2",
582
+ "model.visual.blocks.26.attn.qkv",
583
+ "model.visual.blocks.26.attn.proj",
584
+ "model.visual.blocks.26.mlp.linear_fc1",
585
+ "model.visual.blocks.26.mlp.linear_fc2",
586
+ "model.visual.merger.linear_fc1",
587
+ "model.visual.merger.linear_fc2",
588
+ "model.language_model.layers.0.linear_attn",
589
+ "model.language_model.layers.0.linear_attn.norm",
590
+ "model.language_model.layers.0.linear_attn.in_proj_b",
591
+ "model.language_model.layers.0.linear_attn.in_proj_a",
592
+ "model.language_model.layers.1.linear_attn",
593
+ "model.language_model.layers.1.linear_attn.norm",
594
+ "model.language_model.layers.1.linear_attn.in_proj_b",
595
+ "model.language_model.layers.1.linear_attn.in_proj_a",
596
+ "model.language_model.layers.2.linear_attn",
597
+ "model.language_model.layers.2.linear_attn.norm",
598
+ "model.language_model.layers.2.linear_attn.in_proj_b",
599
+ "model.language_model.layers.2.linear_attn.in_proj_a",
600
+ "model.language_model.layers.4.linear_attn",
601
+ "model.language_model.layers.4.linear_attn.norm",
602
+ "model.language_model.layers.4.linear_attn.in_proj_b",
603
+ "model.language_model.layers.4.linear_attn.in_proj_a",
604
+ "model.language_model.layers.5.linear_attn",
605
+ "model.language_model.layers.5.linear_attn.norm",
606
+ "model.language_model.layers.5.linear_attn.in_proj_b",
607
+ "model.language_model.layers.5.linear_attn.in_proj_a",
608
+ "model.language_model.layers.6.linear_attn",
609
+ "model.language_model.layers.6.linear_attn.norm",
610
+ "model.language_model.layers.6.linear_attn.in_proj_b",
611
+ "model.language_model.layers.6.linear_attn.in_proj_a",
612
+ "model.language_model.layers.8.linear_attn",
613
+ "model.language_model.layers.8.linear_attn.norm",
614
+ "model.language_model.layers.8.linear_attn.in_proj_b",
615
+ "model.language_model.layers.8.linear_attn.in_proj_a",
616
+ "model.language_model.layers.9.linear_attn",
617
+ "model.language_model.layers.9.linear_attn.norm",
618
+ "model.language_model.layers.9.linear_attn.in_proj_b",
619
+ "model.language_model.layers.9.linear_attn.in_proj_a",
620
+ "model.language_model.layers.10.linear_attn",
621
+ "model.language_model.layers.10.linear_attn.norm",
622
+ "model.language_model.layers.10.linear_attn.in_proj_b",
623
+ "model.language_model.layers.10.linear_attn.in_proj_a",
624
+ "model.language_model.layers.12.linear_attn",
625
+ "model.language_model.layers.12.linear_attn.norm",
626
+ "model.language_model.layers.12.linear_attn.in_proj_b",
627
+ "model.language_model.layers.12.linear_attn.in_proj_a",
628
+ "model.language_model.layers.13.linear_attn",
629
+ "model.language_model.layers.13.linear_attn.norm",
630
+ "model.language_model.layers.13.linear_attn.in_proj_b",
631
+ "model.language_model.layers.13.linear_attn.in_proj_a",
632
+ "model.language_model.layers.14.linear_attn",
633
+ "model.language_model.layers.14.linear_attn.norm",
634
+ "model.language_model.layers.14.linear_attn.in_proj_b",
635
+ "model.language_model.layers.14.linear_attn.in_proj_a",
636
+ "model.language_model.layers.16.linear_attn",
637
+ "model.language_model.layers.16.linear_attn.norm",
638
+ "model.language_model.layers.16.linear_attn.in_proj_b",
639
+ "model.language_model.layers.16.linear_attn.in_proj_a",
640
+ "model.language_model.layers.17.linear_attn",
641
+ "model.language_model.layers.17.linear_attn.norm",
642
+ "model.language_model.layers.17.linear_attn.in_proj_b",
643
+ "model.language_model.layers.17.linear_attn.in_proj_a",
644
+ "model.language_model.layers.18.linear_attn",
645
+ "model.language_model.layers.18.linear_attn.norm",
646
+ "model.language_model.layers.18.linear_attn.in_proj_b",
647
+ "model.language_model.layers.18.linear_attn.in_proj_a",
648
+ "model.language_model.layers.20.linear_attn",
649
+ "model.language_model.layers.20.linear_attn.norm",
650
+ "model.language_model.layers.20.linear_attn.in_proj_b",
651
+ "model.language_model.layers.20.linear_attn.in_proj_a",
652
+ "model.language_model.layers.21.linear_attn",
653
+ "model.language_model.layers.21.linear_attn.norm",
654
+ "model.language_model.layers.21.linear_attn.in_proj_b",
655
+ "model.language_model.layers.21.linear_attn.in_proj_a",
656
+ "model.language_model.layers.22.linear_attn",
657
+ "model.language_model.layers.22.linear_attn.norm",
658
+ "model.language_model.layers.22.linear_attn.in_proj_b",
659
+ "model.language_model.layers.22.linear_attn.in_proj_a",
660
+ "model.language_model.layers.24.linear_attn",
661
+ "model.language_model.layers.24.linear_attn.norm",
662
+ "model.language_model.layers.24.linear_attn.in_proj_b",
663
+ "model.language_model.layers.24.linear_attn.in_proj_a",
664
+ "model.language_model.layers.25.linear_attn",
665
+ "model.language_model.layers.25.linear_attn.norm",
666
+ "model.language_model.layers.25.linear_attn.in_proj_b",
667
+ "model.language_model.layers.25.linear_attn.in_proj_a",
668
+ "model.language_model.layers.26.linear_attn",
669
+ "model.language_model.layers.26.linear_attn.norm",
670
+ "model.language_model.layers.26.linear_attn.in_proj_b",
671
+ "model.language_model.layers.26.linear_attn.in_proj_a",
672
+ "model.language_model.layers.28.linear_attn",
673
+ "model.language_model.layers.28.linear_attn.norm",
674
+ "model.language_model.layers.28.linear_attn.in_proj_b",
675
+ "model.language_model.layers.28.linear_attn.in_proj_a",
676
+ "model.language_model.layers.29.linear_attn",
677
+ "model.language_model.layers.29.linear_attn.norm",
678
+ "model.language_model.layers.29.linear_attn.in_proj_b",
679
+ "model.language_model.layers.29.linear_attn.in_proj_a",
680
+ "model.language_model.layers.30.linear_attn",
681
+ "model.language_model.layers.30.linear_attn.norm",
682
+ "model.language_model.layers.30.linear_attn.in_proj_b",
683
+ "model.language_model.layers.30.linear_attn.in_proj_a",
684
+ "model.language_model.layers.32.linear_attn",
685
+ "model.language_model.layers.32.linear_attn.norm",
686
+ "model.language_model.layers.32.linear_attn.in_proj_b",
687
+ "model.language_model.layers.32.linear_attn.in_proj_a",
688
+ "model.language_model.layers.33.linear_attn",
689
+ "model.language_model.layers.33.linear_attn.norm",
690
+ "model.language_model.layers.33.linear_attn.in_proj_b",
691
+ "model.language_model.layers.33.linear_attn.in_proj_a",
692
+ "model.language_model.layers.34.linear_attn",
693
+ "model.language_model.layers.34.linear_attn.norm",
694
+ "model.language_model.layers.34.linear_attn.in_proj_b",
695
+ "model.language_model.layers.34.linear_attn.in_proj_a",
696
+ "model.language_model.layers.36.linear_attn",
697
+ "model.language_model.layers.36.linear_attn.norm",
698
+ "model.language_model.layers.36.linear_attn.in_proj_b",
699
+ "model.language_model.layers.36.linear_attn.in_proj_a",
700
+ "model.language_model.layers.37.linear_attn",
701
+ "model.language_model.layers.37.linear_attn.norm",
702
+ "model.language_model.layers.37.linear_attn.in_proj_b",
703
+ "model.language_model.layers.37.linear_attn.in_proj_a",
704
+ "model.language_model.layers.38.linear_attn",
705
+ "model.language_model.layers.38.linear_attn.norm",
706
+ "model.language_model.layers.38.linear_attn.in_proj_b",
707
+ "model.language_model.layers.38.linear_attn.in_proj_a",
708
+ "model.language_model.layers.40.linear_attn",
709
+ "model.language_model.layers.40.linear_attn.norm",
710
+ "model.language_model.layers.40.linear_attn.in_proj_b",
711
+ "model.language_model.layers.40.linear_attn.in_proj_a",
712
+ "model.language_model.layers.41.linear_attn",
713
+ "model.language_model.layers.41.linear_attn.norm",
714
+ "model.language_model.layers.41.linear_attn.in_proj_b",
715
+ "model.language_model.layers.41.linear_attn.in_proj_a",
716
+ "model.language_model.layers.42.linear_attn",
717
+ "model.language_model.layers.42.linear_attn.norm",
718
+ "model.language_model.layers.42.linear_attn.in_proj_b",
719
+ "model.language_model.layers.42.linear_attn.in_proj_a",
720
+ "model.language_model.layers.44.linear_attn",
721
+ "model.language_model.layers.44.linear_attn.norm",
722
+ "model.language_model.layers.44.linear_attn.in_proj_b",
723
+ "model.language_model.layers.44.linear_attn.in_proj_a",
724
+ "model.language_model.layers.45.linear_attn",
725
+ "model.language_model.layers.45.linear_attn.norm",
726
+ "model.language_model.layers.45.linear_attn.in_proj_b",
727
+ "model.language_model.layers.45.linear_attn.in_proj_a",
728
+ "model.language_model.layers.46.linear_attn",
729
+ "model.language_model.layers.46.linear_attn.norm",
730
+ "model.language_model.layers.46.linear_attn.in_proj_b",
731
+ "model.language_model.layers.46.linear_attn.in_proj_a",
732
+ "model.language_model.layers.48.linear_attn",
733
+ "model.language_model.layers.48.linear_attn.norm",
734
+ "model.language_model.layers.48.linear_attn.in_proj_b",
735
+ "model.language_model.layers.48.linear_attn.in_proj_a",
736
+ "model.language_model.layers.49.linear_attn",
737
+ "model.language_model.layers.49.linear_attn.norm",
738
+ "model.language_model.layers.49.linear_attn.in_proj_b",
739
+ "model.language_model.layers.49.linear_attn.in_proj_a",
740
+ "model.language_model.layers.50.linear_attn",
741
+ "model.language_model.layers.50.linear_attn.norm",
742
+ "model.language_model.layers.50.linear_attn.in_proj_b",
743
+ "model.language_model.layers.50.linear_attn.in_proj_a",
744
+ "model.language_model.layers.52.linear_attn",
745
+ "model.language_model.layers.52.linear_attn.norm",
746
+ "model.language_model.layers.52.linear_attn.in_proj_b",
747
+ "model.language_model.layers.52.linear_attn.in_proj_a",
748
+ "model.language_model.layers.53.linear_attn",
749
+ "model.language_model.layers.53.linear_attn.norm",
750
+ "model.language_model.layers.53.linear_attn.in_proj_b",
751
+ "model.language_model.layers.53.linear_attn.in_proj_a",
752
+ "model.language_model.layers.54.linear_attn",
753
+ "model.language_model.layers.54.linear_attn.norm",
754
+ "model.language_model.layers.54.linear_attn.in_proj_b",
755
+ "model.language_model.layers.54.linear_attn.in_proj_a",
756
+ "model.language_model.layers.56.linear_attn",
757
+ "model.language_model.layers.56.linear_attn.norm",
758
+ "model.language_model.layers.56.linear_attn.in_proj_b",
759
+ "model.language_model.layers.56.linear_attn.in_proj_a",
760
+ "model.language_model.layers.57.linear_attn",
761
+ "model.language_model.layers.57.linear_attn.norm",
762
+ "model.language_model.layers.57.linear_attn.in_proj_b",
763
+ "model.language_model.layers.57.linear_attn.in_proj_a",
764
+ "model.language_model.layers.58.linear_attn",
765
+ "model.language_model.layers.58.linear_attn.norm",
766
+ "model.language_model.layers.58.linear_attn.in_proj_b",
767
+ "model.language_model.layers.58.linear_attn.in_proj_a",
768
+ "model.language_model.layers.60.linear_attn",
769
+ "model.language_model.layers.60.linear_attn.norm",
770
+ "model.language_model.layers.60.linear_attn.in_proj_b",
771
+ "model.language_model.layers.60.linear_attn.in_proj_a",
772
+ "model.language_model.layers.61.linear_attn",
773
+ "model.language_model.layers.61.linear_attn.norm",
774
+ "model.language_model.layers.61.linear_attn.in_proj_b",
775
+ "model.language_model.layers.61.linear_attn.in_proj_a",
776
+ "model.language_model.layers.62.linear_attn",
777
+ "model.language_model.layers.62.linear_attn.norm",
778
+ "model.language_model.layers.62.linear_attn.in_proj_b",
779
+ "model.language_model.layers.62.linear_attn.in_proj_a",
780
+ "lm_head"
781
+ ],
782
+ "kv_cache_scheme": null,
783
+ "quant_method": "compressed-tensors",
784
+ "quantization_status": "compressed",
785
+ "sparsity_config": {},
786
+ "transform_config": {},
787
+ "version": "0.17.2.dev42+g6575dee"
788
+ },
789
+ "text_config": {
790
+ "attention_bias": false,
791
+ "attention_dropout": 0.0,
792
+ "attn_output_gate": true,
793
+ "bos_token_id": 248044,
794
+ "dtype": "bfloat16",
795
+ "eos_token_id": 248044,
796
+ "full_attention_interval": 4,
797
+ "head_dim": 256,
798
+ "hidden_act": "silu",
799
+ "hidden_size": 5120,
800
+ "initializer_range": 0.02,
801
+ "intermediate_size": 17408,
802
+ "layer_types": [
803
+ "linear_attention",
804
+ "linear_attention",
805
+ "linear_attention",
806
+ "full_attention",
807
+ "linear_attention",
808
+ "linear_attention",
809
+ "linear_attention",
810
+ "full_attention",
811
+ "linear_attention",
812
+ "linear_attention",
813
+ "linear_attention",
814
+ "full_attention",
815
+ "linear_attention",
816
+ "linear_attention",
817
+ "linear_attention",
818
+ "full_attention",
819
+ "linear_attention",
820
+ "linear_attention",
821
+ "linear_attention",
822
+ "full_attention",
823
+ "linear_attention",
824
+ "linear_attention",
825
+ "linear_attention",
826
+ "full_attention",
827
+ "linear_attention",
828
+ "linear_attention",
829
+ "linear_attention",
830
+ "full_attention",
831
+ "linear_attention",
832
+ "linear_attention",
833
+ "linear_attention",
834
+ "full_attention",
835
+ "linear_attention",
836
+ "linear_attention",
837
+ "linear_attention",
838
+ "full_attention",
839
+ "linear_attention",
840
+ "linear_attention",
841
+ "linear_attention",
842
+ "full_attention",
843
+ "linear_attention",
844
+ "linear_attention",
845
+ "linear_attention",
846
+ "full_attention",
847
+ "linear_attention",
848
+ "linear_attention",
849
+ "linear_attention",
850
+ "full_attention",
851
+ "linear_attention",
852
+ "linear_attention",
853
+ "linear_attention",
854
+ "full_attention",
855
+ "linear_attention",
856
+ "linear_attention",
857
+ "linear_attention",
858
+ "full_attention",
859
+ "linear_attention",
860
+ "linear_attention",
861
+ "linear_attention",
862
+ "full_attention",
863
+ "linear_attention",
864
+ "linear_attention",
865
+ "linear_attention",
866
+ "full_attention"
867
+ ],
868
+ "linear_conv_kernel_dim": 4,
869
+ "linear_key_head_dim": 128,
870
+ "linear_num_key_heads": 16,
871
+ "linear_num_value_heads": 48,
872
+ "linear_value_head_dim": 128,
873
+ "mamba_ssm_dtype": "float32",
874
+ "max_position_embeddings": 262144,
875
+ "model_type": "qwen3_5_text",
876
+ "mtp_num_hidden_layers": 1,
877
+ "mtp_use_dedicated_embeddings": false,
878
+ "num_attention_heads": 24,
879
+ "num_hidden_layers": 64,
880
+ "num_key_value_heads": 4,
881
+ "output_gate_type": "swish",
882
+ "pad_token_id": null,
883
+ "partial_rotary_factor": 0.25,
884
+ "rms_norm_eps": 1e-06,
885
+ "rope_parameters": {
886
+ "mrope_interleaved": true,
887
+ "mrope_section": [
888
+ 11,
889
+ 11,
890
+ 10
891
+ ],
892
+ "partial_rotary_factor": 0.25,
893
+ "rope_theta": 10000000,
894
+ "rope_type": "default"
895
+ },
896
+ "tie_word_embeddings": false,
897
+ "use_cache": true,
898
+ "vocab_size": 248320
899
+ },
900
+ "tie_word_embeddings": false,
901
+ "transformers_version": "5.14.1",
902
+ "video_token_id": 248057,
903
+ "vision_config": {
904
+ "deepstack_visual_indexes": [],
905
+ "depth": 27,
906
+ "dtype": "bfloat16",
907
+ "hidden_act": "gelu_pytorch_tanh",
908
+ "hidden_size": 1152,
909
+ "in_channels": 3,
910
+ "initializer_range": 0.02,
911
+ "intermediate_size": 4304,
912
+ "model_type": "qwen3_5_vision",
913
+ "num_heads": 16,
914
+ "num_position_embeddings": 2304,
915
+ "out_hidden_size": 5120,
916
+ "patch_size": 16,
917
+ "spatial_merge_size": 2,
918
+ "temporal_patch_size": 2
919
+ },
920
+ "vision_end_token_id": 248054,
921
+ "vision_start_token_id": 248053
922
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 248044,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 248046,
6
+ 248044
7
+ ],
8
+ "pad_token_id": 248044,
9
+ "temperature": 1.0,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "5.14.1"
13
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:994d372da0812952c05a3fb1093db5b1245e314385290892f0dce3883f4c2643
3
+ size 2542796928
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77a9ed7406dccf363131a29bb794ae4c8ff8ef66320fe15bd516b43665afaa4d
3
+ size 4981714744
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d56678eb6bb86df77aff1d21cc3e74a14ac7640a570ea6ed017edc047e02b1e
3
+ size 4997930592
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9e65293ff5d294a1406441b0f4425bad57ca54601763a611a417b72eb74cc68
3
+ size 3000746584
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
processor_config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "do_convert_rgb": true,
4
+ "do_normalize": true,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "image_mean": [
8
+ 0.5,
9
+ 0.5,
10
+ 0.5
11
+ ],
12
+ "image_processor_type": "Qwen2VLImageProcessor",
13
+ "image_std": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "merge_size": 2,
19
+ "patch_size": 16,
20
+ "resample": 3,
21
+ "rescale_factor": 0.00392156862745098,
22
+ "size": {
23
+ "longest_edge": 16777216,
24
+ "shortest_edge": 65536
25
+ },
26
+ "temporal_patch_size": 2
27
+ },
28
+ "processor_class": "Qwen3VLProcessor",
29
+ "video_processor": {
30
+ "do_convert_rgb": true,
31
+ "do_normalize": true,
32
+ "do_rescale": true,
33
+ "do_resize": true,
34
+ "do_sample_frames": true,
35
+ "fps": 2,
36
+ "image_mean": [
37
+ 0.5,
38
+ 0.5,
39
+ 0.5
40
+ ],
41
+ "image_std": [
42
+ 0.5,
43
+ 0.5,
44
+ 0.5
45
+ ],
46
+ "max_frames": 768,
47
+ "merge_size": 2,
48
+ "min_frames": 4,
49
+ "patch_size": 16,
50
+ "resample": 3,
51
+ "rescale_factor": 0.00392156862745098,
52
+ "return_metadata": false,
53
+ "size": {
54
+ "longest_edge": 25165824,
55
+ "shortest_edge": 4096
56
+ },
57
+ "temporal_patch_size": 2,
58
+ "video_processor_type": "Qwen3VLVideoProcessor"
59
+ }
60
+ }
recipe.yaml ADDED
@@ -0,0 +1,265 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ default_stage:
2
+ default_modifiers:
3
+ AutoRoundModifier:
4
+ config_groups:
5
+ group_0:
6
+ targets: [model.language_model.layers.60.linear_attn.in_proj_qkv, model.language_model.layers.60.linear_attn.in_proj_z,
7
+ model.language_model.layers.61.linear_attn.in_proj_qkv, model.language_model.layers.61.linear_attn.in_proj_z,
8
+ model.language_model.layers.62.mlp.gate_proj, model.language_model.layers.62.mlp.up_proj]
9
+ weights:
10
+ num_bits: 2
11
+ type: int
12
+ symmetric: true
13
+ group_size: 128
14
+ strategy: group
15
+ block_structure: null
16
+ dynamic: false
17
+ actorder: null
18
+ scale_dtype: null
19
+ zp_dtype: null
20
+ observer: memoryless_minmax
21
+ observer_kwargs: {}
22
+ input_activations: null
23
+ output_activations: null
24
+ format: null
25
+ group_1:
26
+ targets: [model.language_model.layers.0.linear_attn.in_proj_qkv, model.language_model.layers.0.linear_attn.in_proj_z,
27
+ model.language_model.layers.0.mlp.down_proj, model.language_model.layers.0.mlp.gate_proj,
28
+ model.language_model.layers.0.mlp.up_proj, model.language_model.layers.1.linear_attn.in_proj_qkv,
29
+ model.language_model.layers.1.linear_attn.in_proj_z, model.language_model.layers.1.linear_attn.out_proj,
30
+ model.language_model.layers.1.mlp.down_proj, model.language_model.layers.1.mlp.gate_proj,
31
+ model.language_model.layers.1.mlp.up_proj, model.language_model.layers.10.linear_attn.in_proj_qkv,
32
+ model.language_model.layers.10.linear_attn.in_proj_z, model.language_model.layers.10.linear_attn.out_proj,
33
+ model.language_model.layers.10.mlp.down_proj, model.language_model.layers.10.mlp.gate_proj,
34
+ model.language_model.layers.10.mlp.up_proj, model.language_model.layers.11.mlp.down_proj,
35
+ model.language_model.layers.11.mlp.gate_proj, model.language_model.layers.11.mlp.up_proj,
36
+ model.language_model.layers.11.self_attn.k_proj, model.language_model.layers.11.self_attn.o_proj,
37
+ model.language_model.layers.11.self_attn.q_proj, model.language_model.layers.11.self_attn.v_proj,
38
+ model.language_model.layers.12.linear_attn.in_proj_qkv, model.language_model.layers.12.linear_attn.in_proj_z,
39
+ model.language_model.layers.12.linear_attn.out_proj, model.language_model.layers.12.mlp.down_proj,
40
+ model.language_model.layers.12.mlp.gate_proj, model.language_model.layers.12.mlp.up_proj,
41
+ model.language_model.layers.13.linear_attn.in_proj_qkv, model.language_model.layers.13.linear_attn.in_proj_z,
42
+ model.language_model.layers.13.linear_attn.out_proj, model.language_model.layers.13.mlp.down_proj,
43
+ model.language_model.layers.13.mlp.gate_proj, model.language_model.layers.13.mlp.up_proj,
44
+ model.language_model.layers.14.linear_attn.in_proj_qkv, model.language_model.layers.14.linear_attn.in_proj_z,
45
+ model.language_model.layers.14.linear_attn.out_proj, model.language_model.layers.14.mlp.down_proj,
46
+ model.language_model.layers.14.mlp.gate_proj, model.language_model.layers.14.mlp.up_proj,
47
+ model.language_model.layers.15.mlp.down_proj, model.language_model.layers.15.mlp.gate_proj,
48
+ model.language_model.layers.15.mlp.up_proj, model.language_model.layers.15.self_attn.k_proj,
49
+ model.language_model.layers.15.self_attn.o_proj, model.language_model.layers.15.self_attn.q_proj,
50
+ model.language_model.layers.15.self_attn.v_proj, model.language_model.layers.16.linear_attn.in_proj_qkv,
51
+ model.language_model.layers.16.linear_attn.in_proj_z, model.language_model.layers.16.linear_attn.out_proj,
52
+ model.language_model.layers.16.mlp.down_proj, model.language_model.layers.16.mlp.gate_proj,
53
+ model.language_model.layers.16.mlp.up_proj, model.language_model.layers.17.linear_attn.in_proj_qkv,
54
+ model.language_model.layers.17.linear_attn.in_proj_z, model.language_model.layers.17.linear_attn.out_proj,
55
+ model.language_model.layers.17.mlp.down_proj, model.language_model.layers.17.mlp.gate_proj,
56
+ model.language_model.layers.17.mlp.up_proj, model.language_model.layers.18.linear_attn.in_proj_qkv,
57
+ model.language_model.layers.18.linear_attn.in_proj_z, model.language_model.layers.18.linear_attn.out_proj,
58
+ model.language_model.layers.18.mlp.down_proj, model.language_model.layers.18.mlp.gate_proj,
59
+ model.language_model.layers.18.mlp.up_proj, model.language_model.layers.19.mlp.down_proj,
60
+ model.language_model.layers.19.mlp.gate_proj, model.language_model.layers.19.mlp.up_proj,
61
+ model.language_model.layers.19.self_attn.k_proj, model.language_model.layers.19.self_attn.o_proj,
62
+ model.language_model.layers.19.self_attn.q_proj, model.language_model.layers.19.self_attn.v_proj,
63
+ model.language_model.layers.2.linear_attn.in_proj_qkv, model.language_model.layers.2.linear_attn.in_proj_z,
64
+ model.language_model.layers.2.linear_attn.out_proj, model.language_model.layers.2.mlp.down_proj,
65
+ model.language_model.layers.2.mlp.gate_proj, model.language_model.layers.2.mlp.up_proj,
66
+ model.language_model.layers.20.linear_attn.in_proj_qkv, model.language_model.layers.20.linear_attn.in_proj_z,
67
+ model.language_model.layers.20.linear_attn.out_proj, model.language_model.layers.20.mlp.down_proj,
68
+ model.language_model.layers.20.mlp.gate_proj, model.language_model.layers.20.mlp.up_proj,
69
+ model.language_model.layers.21.linear_attn.in_proj_qkv, model.language_model.layers.21.linear_attn.in_proj_z,
70
+ model.language_model.layers.21.linear_attn.out_proj, model.language_model.layers.21.mlp.down_proj,
71
+ model.language_model.layers.21.mlp.gate_proj, model.language_model.layers.21.mlp.up_proj,
72
+ model.language_model.layers.22.linear_attn.in_proj_qkv, model.language_model.layers.22.linear_attn.in_proj_z,
73
+ model.language_model.layers.22.linear_attn.out_proj, model.language_model.layers.22.mlp.down_proj,
74
+ model.language_model.layers.22.mlp.gate_proj, model.language_model.layers.22.mlp.up_proj,
75
+ model.language_model.layers.23.mlp.down_proj, model.language_model.layers.23.mlp.gate_proj,
76
+ model.language_model.layers.23.mlp.up_proj, model.language_model.layers.23.self_attn.k_proj,
77
+ model.language_model.layers.23.self_attn.o_proj, model.language_model.layers.23.self_attn.q_proj,
78
+ model.language_model.layers.23.self_attn.v_proj, model.language_model.layers.24.linear_attn.in_proj_qkv,
79
+ model.language_model.layers.24.linear_attn.in_proj_z, model.language_model.layers.24.linear_attn.out_proj,
80
+ model.language_model.layers.24.mlp.down_proj, model.language_model.layers.24.mlp.gate_proj,
81
+ model.language_model.layers.24.mlp.up_proj, model.language_model.layers.25.linear_attn.in_proj_qkv,
82
+ model.language_model.layers.25.linear_attn.in_proj_z, model.language_model.layers.25.linear_attn.out_proj,
83
+ model.language_model.layers.25.mlp.down_proj, model.language_model.layers.25.mlp.gate_proj,
84
+ model.language_model.layers.25.mlp.up_proj, model.language_model.layers.26.linear_attn.in_proj_qkv,
85
+ model.language_model.layers.26.linear_attn.in_proj_z, model.language_model.layers.26.linear_attn.out_proj,
86
+ model.language_model.layers.26.mlp.down_proj, model.language_model.layers.26.mlp.gate_proj,
87
+ model.language_model.layers.26.mlp.up_proj, model.language_model.layers.27.mlp.down_proj,
88
+ model.language_model.layers.27.mlp.gate_proj, model.language_model.layers.27.mlp.up_proj,
89
+ model.language_model.layers.27.self_attn.k_proj, model.language_model.layers.27.self_attn.o_proj,
90
+ model.language_model.layers.27.self_attn.q_proj, model.language_model.layers.27.self_attn.v_proj,
91
+ model.language_model.layers.28.linear_attn.in_proj_qkv, model.language_model.layers.28.linear_attn.in_proj_z,
92
+ model.language_model.layers.28.linear_attn.out_proj, model.language_model.layers.28.mlp.down_proj,
93
+ model.language_model.layers.28.mlp.gate_proj, model.language_model.layers.28.mlp.up_proj,
94
+ model.language_model.layers.29.linear_attn.in_proj_qkv, model.language_model.layers.29.linear_attn.in_proj_z,
95
+ model.language_model.layers.29.linear_attn.out_proj, model.language_model.layers.29.mlp.down_proj,
96
+ model.language_model.layers.29.mlp.gate_proj, model.language_model.layers.29.mlp.up_proj,
97
+ model.language_model.layers.3.mlp.down_proj, model.language_model.layers.3.mlp.gate_proj,
98
+ model.language_model.layers.3.mlp.up_proj, model.language_model.layers.3.self_attn.k_proj,
99
+ model.language_model.layers.3.self_attn.o_proj, model.language_model.layers.3.self_attn.q_proj,
100
+ model.language_model.layers.3.self_attn.v_proj, model.language_model.layers.30.linear_attn.in_proj_qkv,
101
+ model.language_model.layers.30.linear_attn.in_proj_z, model.language_model.layers.30.linear_attn.out_proj,
102
+ model.language_model.layers.30.mlp.down_proj, model.language_model.layers.30.mlp.gate_proj,
103
+ model.language_model.layers.30.mlp.up_proj, model.language_model.layers.31.mlp.down_proj,
104
+ model.language_model.layers.31.mlp.gate_proj, model.language_model.layers.31.mlp.up_proj,
105
+ model.language_model.layers.31.self_attn.k_proj, model.language_model.layers.31.self_attn.o_proj,
106
+ model.language_model.layers.31.self_attn.q_proj, model.language_model.layers.31.self_attn.v_proj,
107
+ model.language_model.layers.32.linear_attn.in_proj_qkv, model.language_model.layers.32.linear_attn.in_proj_z,
108
+ model.language_model.layers.32.linear_attn.out_proj, model.language_model.layers.32.mlp.down_proj,
109
+ model.language_model.layers.32.mlp.gate_proj, model.language_model.layers.32.mlp.up_proj,
110
+ model.language_model.layers.33.linear_attn.in_proj_qkv, model.language_model.layers.33.linear_attn.in_proj_z,
111
+ model.language_model.layers.33.linear_attn.out_proj, model.language_model.layers.33.mlp.down_proj,
112
+ model.language_model.layers.33.mlp.gate_proj, model.language_model.layers.33.mlp.up_proj,
113
+ model.language_model.layers.34.linear_attn.in_proj_qkv, model.language_model.layers.34.linear_attn.in_proj_z,
114
+ model.language_model.layers.34.linear_attn.out_proj, model.language_model.layers.34.mlp.down_proj,
115
+ model.language_model.layers.34.mlp.gate_proj, model.language_model.layers.34.mlp.up_proj,
116
+ model.language_model.layers.35.mlp.down_proj, model.language_model.layers.35.mlp.gate_proj,
117
+ model.language_model.layers.35.mlp.up_proj, model.language_model.layers.35.self_attn.k_proj,
118
+ model.language_model.layers.35.self_attn.o_proj, model.language_model.layers.35.self_attn.q_proj,
119
+ model.language_model.layers.35.self_attn.v_proj, model.language_model.layers.36.linear_attn.in_proj_qkv,
120
+ model.language_model.layers.36.linear_attn.in_proj_z, model.language_model.layers.36.linear_attn.out_proj,
121
+ model.language_model.layers.36.mlp.down_proj, model.language_model.layers.36.mlp.gate_proj,
122
+ model.language_model.layers.36.mlp.up_proj, model.language_model.layers.37.linear_attn.in_proj_qkv,
123
+ model.language_model.layers.37.linear_attn.in_proj_z, model.language_model.layers.37.linear_attn.out_proj,
124
+ model.language_model.layers.37.mlp.down_proj, model.language_model.layers.37.mlp.gate_proj,
125
+ model.language_model.layers.37.mlp.up_proj, model.language_model.layers.38.linear_attn.in_proj_qkv,
126
+ model.language_model.layers.38.linear_attn.in_proj_z, model.language_model.layers.38.linear_attn.out_proj,
127
+ model.language_model.layers.38.mlp.down_proj, model.language_model.layers.38.mlp.gate_proj,
128
+ model.language_model.layers.38.mlp.up_proj, model.language_model.layers.39.mlp.down_proj,
129
+ model.language_model.layers.39.mlp.gate_proj, model.language_model.layers.39.mlp.up_proj,
130
+ model.language_model.layers.39.self_attn.k_proj, model.language_model.layers.39.self_attn.o_proj,
131
+ model.language_model.layers.39.self_attn.q_proj, model.language_model.layers.39.self_attn.v_proj,
132
+ model.language_model.layers.4.linear_attn.in_proj_qkv, model.language_model.layers.4.linear_attn.in_proj_z,
133
+ model.language_model.layers.4.linear_attn.out_proj, model.language_model.layers.4.mlp.down_proj,
134
+ model.language_model.layers.4.mlp.gate_proj, model.language_model.layers.4.mlp.up_proj,
135
+ model.language_model.layers.40.linear_attn.in_proj_qkv, model.language_model.layers.40.linear_attn.in_proj_z,
136
+ model.language_model.layers.40.linear_attn.out_proj, model.language_model.layers.40.mlp.down_proj,
137
+ model.language_model.layers.40.mlp.gate_proj, model.language_model.layers.40.mlp.up_proj,
138
+ model.language_model.layers.41.linear_attn.in_proj_qkv, model.language_model.layers.41.linear_attn.in_proj_z,
139
+ model.language_model.layers.41.linear_attn.out_proj, model.language_model.layers.41.mlp.down_proj,
140
+ model.language_model.layers.41.mlp.gate_proj, model.language_model.layers.41.mlp.up_proj,
141
+ model.language_model.layers.42.linear_attn.in_proj_qkv, model.language_model.layers.42.linear_attn.in_proj_z,
142
+ model.language_model.layers.42.linear_attn.out_proj, model.language_model.layers.42.mlp.down_proj,
143
+ model.language_model.layers.42.mlp.gate_proj, model.language_model.layers.42.mlp.up_proj,
144
+ model.language_model.layers.43.mlp.down_proj, model.language_model.layers.43.mlp.gate_proj,
145
+ model.language_model.layers.43.mlp.up_proj, model.language_model.layers.43.self_attn.k_proj,
146
+ model.language_model.layers.43.self_attn.o_proj, model.language_model.layers.43.self_attn.q_proj,
147
+ model.language_model.layers.43.self_attn.v_proj, model.language_model.layers.44.linear_attn.in_proj_qkv,
148
+ model.language_model.layers.44.linear_attn.in_proj_z, model.language_model.layers.44.linear_attn.out_proj,
149
+ model.language_model.layers.44.mlp.down_proj, model.language_model.layers.44.mlp.gate_proj,
150
+ model.language_model.layers.44.mlp.up_proj, model.language_model.layers.45.linear_attn.in_proj_qkv,
151
+ model.language_model.layers.45.linear_attn.in_proj_z, model.language_model.layers.45.linear_attn.out_proj,
152
+ model.language_model.layers.45.mlp.down_proj, model.language_model.layers.45.mlp.gate_proj,
153
+ model.language_model.layers.45.mlp.up_proj, model.language_model.layers.46.linear_attn.in_proj_qkv,
154
+ model.language_model.layers.46.linear_attn.in_proj_z, model.language_model.layers.46.linear_attn.out_proj,
155
+ model.language_model.layers.46.mlp.down_proj, model.language_model.layers.46.mlp.gate_proj,
156
+ model.language_model.layers.46.mlp.up_proj, model.language_model.layers.47.mlp.down_proj,
157
+ model.language_model.layers.47.mlp.gate_proj, model.language_model.layers.47.mlp.up_proj,
158
+ model.language_model.layers.47.self_attn.k_proj, model.language_model.layers.47.self_attn.o_proj,
159
+ model.language_model.layers.47.self_attn.q_proj, model.language_model.layers.47.self_attn.v_proj,
160
+ model.language_model.layers.48.linear_attn.in_proj_qkv, model.language_model.layers.48.linear_attn.in_proj_z,
161
+ model.language_model.layers.48.linear_attn.out_proj, model.language_model.layers.48.mlp.down_proj,
162
+ model.language_model.layers.48.mlp.gate_proj, model.language_model.layers.48.mlp.up_proj,
163
+ model.language_model.layers.49.linear_attn.in_proj_qkv, model.language_model.layers.49.linear_attn.in_proj_z,
164
+ model.language_model.layers.49.linear_attn.out_proj, model.language_model.layers.49.mlp.down_proj,
165
+ model.language_model.layers.49.mlp.gate_proj, model.language_model.layers.49.mlp.up_proj,
166
+ model.language_model.layers.5.linear_attn.in_proj_qkv, model.language_model.layers.5.linear_attn.in_proj_z,
167
+ model.language_model.layers.5.linear_attn.out_proj, model.language_model.layers.5.mlp.down_proj,
168
+ model.language_model.layers.5.mlp.gate_proj, model.language_model.layers.5.mlp.up_proj,
169
+ model.language_model.layers.50.linear_attn.in_proj_qkv, model.language_model.layers.50.linear_attn.in_proj_z,
170
+ model.language_model.layers.50.linear_attn.out_proj, model.language_model.layers.50.mlp.down_proj,
171
+ model.language_model.layers.50.mlp.gate_proj, model.language_model.layers.50.mlp.up_proj,
172
+ model.language_model.layers.51.mlp.down_proj, model.language_model.layers.51.mlp.gate_proj,
173
+ model.language_model.layers.51.mlp.up_proj, model.language_model.layers.51.self_attn.k_proj,
174
+ model.language_model.layers.51.self_attn.o_proj, model.language_model.layers.51.self_attn.q_proj,
175
+ model.language_model.layers.51.self_attn.v_proj, model.language_model.layers.52.linear_attn.in_proj_qkv,
176
+ model.language_model.layers.52.linear_attn.in_proj_z, model.language_model.layers.52.linear_attn.out_proj,
177
+ model.language_model.layers.52.mlp.down_proj, model.language_model.layers.52.mlp.gate_proj,
178
+ model.language_model.layers.52.mlp.up_proj, model.language_model.layers.53.linear_attn.in_proj_qkv,
179
+ model.language_model.layers.53.linear_attn.in_proj_z, model.language_model.layers.53.linear_attn.out_proj,
180
+ model.language_model.layers.53.mlp.down_proj, model.language_model.layers.53.mlp.gate_proj,
181
+ model.language_model.layers.53.mlp.up_proj, model.language_model.layers.54.linear_attn.in_proj_qkv,
182
+ model.language_model.layers.54.linear_attn.in_proj_z, model.language_model.layers.54.linear_attn.out_proj,
183
+ model.language_model.layers.54.mlp.down_proj, model.language_model.layers.54.mlp.gate_proj,
184
+ model.language_model.layers.54.mlp.up_proj, model.language_model.layers.55.mlp.down_proj,
185
+ model.language_model.layers.55.mlp.gate_proj, model.language_model.layers.55.mlp.up_proj,
186
+ model.language_model.layers.55.self_attn.k_proj, model.language_model.layers.55.self_attn.o_proj,
187
+ model.language_model.layers.55.self_attn.q_proj, model.language_model.layers.55.self_attn.v_proj,
188
+ model.language_model.layers.56.linear_attn.in_proj_qkv, model.language_model.layers.56.linear_attn.in_proj_z,
189
+ model.language_model.layers.56.linear_attn.out_proj, model.language_model.layers.56.mlp.down_proj,
190
+ model.language_model.layers.56.mlp.gate_proj, model.language_model.layers.56.mlp.up_proj,
191
+ model.language_model.layers.57.linear_attn.in_proj_qkv, model.language_model.layers.57.linear_attn.in_proj_z,
192
+ model.language_model.layers.57.linear_attn.out_proj, model.language_model.layers.57.mlp.down_proj,
193
+ model.language_model.layers.57.mlp.gate_proj, model.language_model.layers.57.mlp.up_proj,
194
+ model.language_model.layers.58.linear_attn.in_proj_qkv, model.language_model.layers.58.linear_attn.in_proj_z,
195
+ model.language_model.layers.58.linear_attn.out_proj, model.language_model.layers.58.mlp.down_proj,
196
+ model.language_model.layers.58.mlp.gate_proj, model.language_model.layers.58.mlp.up_proj,
197
+ model.language_model.layers.59.mlp.down_proj, model.language_model.layers.59.mlp.gate_proj,
198
+ model.language_model.layers.59.mlp.up_proj, model.language_model.layers.59.self_attn.k_proj,
199
+ model.language_model.layers.59.self_attn.o_proj, model.language_model.layers.59.self_attn.q_proj,
200
+ model.language_model.layers.59.self_attn.v_proj, model.language_model.layers.6.linear_attn.in_proj_qkv,
201
+ model.language_model.layers.6.linear_attn.in_proj_z, model.language_model.layers.6.linear_attn.out_proj,
202
+ model.language_model.layers.6.mlp.down_proj, model.language_model.layers.6.mlp.gate_proj,
203
+ model.language_model.layers.6.mlp.up_proj, model.language_model.layers.60.linear_attn.out_proj,
204
+ model.language_model.layers.60.mlp.down_proj, model.language_model.layers.60.mlp.gate_proj,
205
+ model.language_model.layers.60.mlp.up_proj, model.language_model.layers.61.linear_attn.out_proj,
206
+ model.language_model.layers.61.mlp.down_proj, model.language_model.layers.61.mlp.gate_proj,
207
+ model.language_model.layers.61.mlp.up_proj, model.language_model.layers.62.linear_attn.in_proj_qkv,
208
+ model.language_model.layers.62.linear_attn.in_proj_z, model.language_model.layers.62.linear_attn.out_proj,
209
+ model.language_model.layers.62.mlp.down_proj, model.language_model.layers.63.mlp.down_proj,
210
+ model.language_model.layers.63.mlp.gate_proj, model.language_model.layers.63.mlp.up_proj,
211
+ model.language_model.layers.63.self_attn.k_proj, model.language_model.layers.63.self_attn.o_proj,
212
+ model.language_model.layers.63.self_attn.q_proj, model.language_model.layers.63.self_attn.v_proj,
213
+ model.language_model.layers.7.mlp.down_proj, model.language_model.layers.7.mlp.gate_proj,
214
+ model.language_model.layers.7.mlp.up_proj, model.language_model.layers.7.self_attn.k_proj,
215
+ model.language_model.layers.7.self_attn.o_proj, model.language_model.layers.7.self_attn.q_proj,
216
+ model.language_model.layers.7.self_attn.v_proj, model.language_model.layers.8.linear_attn.in_proj_qkv,
217
+ model.language_model.layers.8.linear_attn.in_proj_z, model.language_model.layers.8.linear_attn.out_proj,
218
+ model.language_model.layers.8.mlp.down_proj, model.language_model.layers.8.mlp.gate_proj,
219
+ model.language_model.layers.8.mlp.up_proj, model.language_model.layers.9.linear_attn.in_proj_qkv,
220
+ model.language_model.layers.9.linear_attn.in_proj_z, model.language_model.layers.9.linear_attn.out_proj,
221
+ model.language_model.layers.9.mlp.down_proj, model.language_model.layers.9.mlp.gate_proj,
222
+ model.language_model.layers.9.mlp.up_proj]
223
+ weights:
224
+ num_bits: 3
225
+ type: int
226
+ symmetric: true
227
+ group_size: 128
228
+ strategy: group
229
+ block_structure: null
230
+ dynamic: false
231
+ actorder: null
232
+ scale_dtype: null
233
+ zp_dtype: null
234
+ observer: memoryless_minmax
235
+ observer_kwargs: {}
236
+ input_activations: null
237
+ output_activations: null
238
+ format: null
239
+ group_2:
240
+ targets: [model.language_model.layers.0.linear_attn.out_proj]
241
+ weights:
242
+ num_bits: 4
243
+ type: int
244
+ symmetric: true
245
+ group_size: 128
246
+ strategy: group
247
+ block_structure: null
248
+ dynamic: false
249
+ actorder: null
250
+ scale_dtype: null
251
+ zp_dtype: null
252
+ observer: memoryless_minmax
253
+ observer_kwargs: {}
254
+ input_activations: null
255
+ output_activations: null
256
+ format: null
257
+ targets: [Linear]
258
+ ignore: []
259
+ bypass_divisibility_checks: false
260
+ requires_calibration_data: true
261
+ iters: 512
262
+ enable_torch_compile: true
263
+ batch_size: 1
264
+ device_ids: '0'
265
+ disable_opt_rtn: false
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
3
+ size 19989325
tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "audio_bos_token": "<|audio_start|>",
4
+ "audio_eos_token": "<|audio_end|>",
5
+ "audio_token": "<|audio_pad|>",
6
+ "backend": "tokenizers",
7
+ "bos_token": null,
8
+ "clean_up_tokenization_spaces": false,
9
+ "eos_token": "<|im_end|>",
10
+ "errors": "replace",
11
+ "image_token": "<|image_pad|>",
12
+ "is_local": true,
13
+ "local_files_only": false,
14
+ "model_max_length": 262144,
15
+ "model_specific_special_tokens": {
16
+ "audio_bos_token": "<|audio_start|>",
17
+ "audio_eos_token": "<|audio_end|>",
18
+ "audio_token": "<|audio_pad|>",
19
+ "image_token": "<|image_pad|>",
20
+ "video_token": "<|video_pad|>",
21
+ "vision_bos_token": "<|vision_start|>",
22
+ "vision_eos_token": "<|vision_end|>"
23
+ },
24
+ "pad_token": "<|endoftext|>",
25
+ "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
26
+ "processor_class": "Qwen3VLProcessor",
27
+ "split_special_tokens": false,
28
+ "tokenizer_class": "Qwen2Tokenizer",
29
+ "unk_token": null,
30
+ "video_token": "<|video_pad|>",
31
+ "vision_bos_token": "<|vision_start|>",
32
+ "vision_eos_token": "<|vision_end|>"
33
+ }